菜单
SkillsMP 已收集 minghinmatthewlam/agent-guards 中的 13 个 Skill。打开任一 Skill 可查看来源和详情。
已展示 13 / 13 个已收集 Skill。
Create a self-contained HTML explanation when the user requests one or when important, durable project knowledge is materially easier to understand visually than in concise chat. Use for significant architecture, research, decisions, incidents, audits, or…
原文语言：英语
Present concise plans, progress updates, findings, and final reports that keep the human oriented, informed, and able to learn how the project works. Use for complex agent coding work and focus on the most important points and decisions.
原文语言：英语
Run the bundled OpenClaw structured code-review helper for local changes, branches, commits, and PRs. Use for ordinary code-review requests, default closeout review, or an explicitly requested Codex/Claude review panel.
原文语言：英语
Find important, high-confidence correctness bugs and edge cases in an existing codebase. Use when the user asks to inspect a repository, subsystem, or implementation for bugs, failure modes, incorrect behavior, or overlooked edge cases.
原文语言：英语
Coordinate complex work across workers while keeping product context and final judgment in the main session. Use when the user asks to orchestrate, delegate, parallelize, supervise workers, or coordinate multi-agent implementation, research, review, or…
原文语言：英语
Clarify a new task by stating the goal the agent believes the user wants, showing its current understanding, and asking only product-related or high-priority questions that could materially change the outcome. Use before planning or implementation when the…
原文语言：英语
Develop and debug iOS apps with the xcodebuildmcp CLI using simulator-first build, test, run, log, UI-inspection, and device workflows. Use for ordinary iOS development, build or test failures, runtime crashes, simulator problems, and iterative fix/verify…
原文语言：英语
Run a preflight-gated iOS release with asc for TestFlight or App Store delivery. Use when preparing, validating, publishing, submitting, diagnosing blockers, or creating a repeatable iOS release workflow.
原文语言：英语
Diagnose a concrete model mistake and improve the code, tests, instructions, skills, tools, or workflow so the same class of failure is less likely to recur, then retry the original task. Use when the user explicitly invokes /learn-from-mistake or asks the…
原文语言：英语
Audit agent skills for triggering quality, correctness, context efficiency, redundancy, structure, failure guidance, and coverage gaps. Use when the user asks to review, improve, compare, simplify, or evaluate skills in global, repo-local, Claude, Codex, or…
原文语言：英语
Run an autonomous, verifiable continuation loop for implementation, product, QA, cleanup, refactor, evaluation, performance, or research goals. Use when the user asks for /use-loop, loop mode, repeated attempts, retry-until-green work, or a non-trivial goal…
原文语言：英语
Verify the actual material evidence behind a selected assertion, claim, finding, or final result. Use when the user explicitly invokes evidence or asks to substantiate, prove, check, or challenge something an agent reported.
原文语言：英语
Prove the requested goal works on the highest-signal affected surface before closing. Default closing behavior for every implementation task — not just when explicitly asked. Also triggers on: 'make sure it works', 'test it yourself', 'don't just tell me it's…
原文语言：英语